tadamcz | Dark Hacker News

user:	tadamcz
created:	October 6, 2022
karma:	50
about:	Senior research engineer at Epoch AI website: https://tadamcz.com/ email: tadamczewskipublic@gmail.com

1.	Claude can't stop itself from writing code comments(bayes.net) 1 points by tadamcz 22 days ago \| 2 comments
2.	Testing AIs on 68 of the hardest open Erdos problems, verified in Lean(arxiv.org) 3 points by tadamcz 23 days ago \| 0 comments
3.	AI proof of the Erdős–Sós conjecture(arxiv.org) 6 points by tadamcz 23 days ago \| 0 comments
4.	OEIS Open: A benchmark of 492 unsolved math conjectures, formalized in Lean(arxiv.org) 2 points by tadamcz 61 days ago \| 0 comments
5.	MirrorCode: What's the largest software project AI can complete on its own?(epoch.ai) 4 points by tadamcz 112 days ago \| 1 comment
6.	MirrorCode: Evidence that AI can do some weeks-long coding tasks(epoch.ai) 3 points by tadamcz 189 days ago \| 0 comments
7.	Claude 4 Sonnet hacked SWE-bench by peeking at future commits(bayes.net) 3 points by tadamcz 1 year ago \| 1 comment
8.	Open database of AI benchmark results with raw evaluation logs(epoch.ai) 1 points by tadamcz 1 year ago \| 1 comment